Instructions to use unsloth/DeepSeek-R1-Zero-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-R1-Zero-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/DeepSeek-R1-Zero-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/DeepSeek-R1-Zero-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/DeepSeek-R1-Zero-GGUF",
	filename="DeepSeek-R1-Zero-Q2_K_L/DeepSeek-R1-Zero-Q2_K_L-00001-of-00005.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use unsloth/DeepSeek-R1-Zero-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use unsloth/DeepSeek-R1-Zero-GGUF with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M
```

Unsloth Studio new

How to use unsloth/DeepSeek-R1-Zero-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-R1-Zero-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-R1-Zero-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/DeepSeek-R1-Zero-GGUF to start chatting

Docker Model Runner
How to use unsloth/DeepSeek-R1-Zero-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M
```

Lemonade

How to use unsloth/DeepSeek-R1-Zero-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-R1-Zero-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Zero-GGUF-Q4_K_M

List all available models

lemonade list

danielhanchen commited on Jan 20, 2025

Commit

1a5b839

verified ·

1 Parent(s): 250d329

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -15,11 +15,11 @@ tags:
 Or you can view more detailed instructions here: [unsloth.ai/blog/deepseek-r1](https://unsloth.ai/blog/deepseek-r1)
 1. Do not forget about `<｜User｜>` and `<｜Assistant｜>` tokens! - Or use a chat template formatter
 2. Obtain the latest `llama.cpp` at https://github.com/ggerganov/llama.cpp
-3. Example with Q8_0 K quantized cache **Notice -no-cnv disables auto conversation mode**
    ```bash
    ./llama.cpp/llama-cli \
-       --model unsloth/DeepSeek-R1-GGUF/DeepSeek-R1-Q4_K_M.gguf \
-       --cache-type-k q8_0 \
        --threads 16 \
        --prompt '<｜User｜>What is 1+1?<｜Assistant｜>' \
        -no-cnv
@@ -38,8 +38,8 @@ Or you can view more detailed instructions here: [unsloth.ai/blog/deepseek-r1](h
 4. If you have a GPU (RTX 4090 for example) with 24GB, you can offload multiple layers to the GPU for faster processing. If you have multiple GPUs, you can probably offload more layers.
    ```bash
    ./llama.cpp/llama-cli \
-   --model unsloth/DeepSeek-R1-GGUF/DeepSeek-R1-Q4_K_M.gguf
-   --cache-type-k q8_0
    --threads 16
    --prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
    --n-gpu-layers 20 \

 Or you can view more detailed instructions here: [unsloth.ai/blog/deepseek-r1](https://unsloth.ai/blog/deepseek-r1)
 1. Do not forget about `<｜User｜>` and `<｜Assistant｜>` tokens! - Or use a chat template formatter
 2. Obtain the latest `llama.cpp` at https://github.com/ggerganov/llama.cpp
+3. Example with Q5_0 K quantized cache **Notice -no-cnv disables auto conversation mode**
    ```bash
    ./llama.cpp/llama-cli \
+       --model unsloth/DeepSeek-R1-GGUF/DeepSeek-R1-Q2_K_XS.gguf \
+       --cache-type-k q5_0 \
        --threads 16 \
        --prompt '<｜User｜>What is 1+1?<｜Assistant｜>' \
        -no-cnv
 4. If you have a GPU (RTX 4090 for example) with 24GB, you can offload multiple layers to the GPU for faster processing. If you have multiple GPUs, you can probably offload more layers.
    ```bash
    ./llama.cpp/llama-cli \
+   --model unsloth/DeepSeek-R1-GGUF/DeepSeek-R1-Q2_K_XS.gguf
+   --cache-type-k q5_0
    --threads 16
    --prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
    --n-gpu-layers 20 \